Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 1575
    Prev
    Next
    INDEX
    Explanations

    mentions of interfaces in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     chré
    -0.83
     propOrder
    -0.81
     russes
    -0.79
     GenerationType
    -0.79
     sauvages
    -0.77
    odyear
    -0.77
    avocat
    -0.76
     paille
    -0.75
     dépens
    -0.75
     geolog
    -0.74
    POSITIVE LOGITS
     interfaces
    2.43
     interface
    2.39
    Interface
    2.28
     Interface
    2.24
     Interfaces
    2.07
    interface
    2.07
     INTERFACE
    2.04
    Interfaces
    1.95
    INTERFACE
    1.87
    interfaces
    1.83
    Activations Density 0.026%

    No Known Activations